[PATCH v3 5/6] ARM: rockchip: add basic smp support for rk3288

[Kever Yang]

This patch add basic rk3288 smp support.

Only cortex-A9 need invalid L1, A7/A12/A15/A17 should not invalid L1, since
for A7/A12/A15, the invalidation would be taken as clean and invalidate.

If you use the software manual invalidation instead of hardware invalidation
(assert l1/l2rstdisable during reset) after reset, there is tiny change that
some cachelines would be in dirty and valid state after reset(since the ram
content would be random value after reset), then the unexpected clean might
lead to system crash.

Signed-off-by: Heiko Stuebner <heiko at sntech.de>
Signed-off-by: Kever Yang <kever.yang at rock-chips.com>
---

Changes in v3:
- use one ops and secondary_starup for all rockchip SOCs
- pick back the power domain operation for cpu hotplug

Changes in v2:
- use rk3288_boot_secondary instead ofsmp_boot_secondary
- discards the power domain operation
- handle the per cpu starup when actived by 'sev'

 arch/arm/mach-rockchip/headsmp.S |  5 ++-
 arch/arm/mach-rockchip/platsmp.c | 81 ++++++++++++++++++++++++++++------------
 2 files changed, 61 insertions(+), 25 deletions(-)

diff --git a/arch/arm/mach-rockchip/headsmp.S b/arch/arm/mach-rockchip/headsmp.S
index 73206e3..46c22de 100644
--- a/arch/arm/mach-rockchip/headsmp.S
+++ b/arch/arm/mach-rockchip/headsmp.S
@@ -16,7 +16,10 @@
 #include <linux/init.h>
 
 ENTRY(rockchip_secondary_startup)
-	bl	v7_invalidate_l1
+	mrc	p15, 0, r0, c0, c0, 0	@ read main ID register
+	ldr	r1, =0x00000c09		@ Cortex-A9 primary part number
+	teq	r0, r1
+	beq	v7_invalidate_l1
 	b	secondary_startup
 ENDPROC(rockchip_secondary_startup)
 
diff --git a/arch/arm/mach-rockchip/platsmp.c b/arch/arm/mach-rockchip/platsmp.c
index 57b53b3..d1f858e 100644
--- a/arch/arm/mach-rockchip/platsmp.c
+++ b/arch/arm/mach-rockchip/platsmp.c
@@ -84,6 +84,8 @@ static int pmu_set_power_domain(int pd, bool on)
 static int __cpuinit rockchip_boot_secondary(unsigned int cpu,
 					     struct task_struct *idle)
 {
+	int ret;
+
 	if (!sram_base_addr || !pmu) {
 		pr_err("%s: sram or pmu missing for cpu boot\n", __func__);
 		return -ENXIO;
@@ -96,7 +98,26 @@ static int __cpuinit rockchip_boot_secondary(unsigned int cpu,
 	}
 
 	/* start the core */
-	return pmu_set_power_domain(0 + cpu, true);
+	ret = pmu_set_power_domain(0 + cpu, true);
+	if (ret < 0)
+		return ret;
+
+	if (read_cpuid_part() != ARM_CPU_PART_CORTEX_A9) {
+		/* We communicate with the bootrom to active the cpus other
+		 * than cpu0, after a blob of initialize code, they will
+		 * stay at wfe state, once they are actived, they will check
+		 * the mailbox:
+		 * sram_base_addr + 4: 0xdeadbeaf
+		 * sram_base_addr + 8: start address for pc
+		 * */
+		udelay(10);
+		writel(virt_to_phys(rockchip_secondary_startup),
+			sram_base_addr + 8);
+		writel(0xDEADBEAF, sram_base_addr + 4);
+		dsb_sev();
+	}
+
+	return 0;
 }
 
 /**
@@ -129,8 +150,6 @@ static int __init rockchip_smp_prepare_sram(struct device_node *node)
 		return -EINVAL;
 	}
 
-	sram_base_addr = of_iomap(node, 0);
-
 	/* set the boot function for the sram code */
 	rockchip_boot_fn = virt_to_phys(rockchip_secondary_startup);
 
@@ -203,18 +222,7 @@ static void __init rockchip_smp_prepare_cpus(unsigned int max_cpus)
 {
 	struct device_node *node;
 	unsigned int i;
-
-	node = of_find_compatible_node(NULL, NULL, "arm,cortex-a9-scu");
-	if (!node) {
-		pr_err("%s: missing scu\n", __func__);
-		return;
-	}
-
-	scu_base_addr = of_iomap(node, 0);
-	if (!scu_base_addr) {
-		pr_err("%s: could not map scu registers\n", __func__);
-		return;
-	}
+	unsigned int l2ctlr;
 
 	node = of_find_compatible_node(NULL, NULL, "rockchip,rk3066-smp-sram");
 	if (!node) {
@@ -222,22 +230,47 @@ static void __init rockchip_smp_prepare_cpus(unsigned int max_cpus)
 		return;
 	}
 
-	if (rockchip_smp_prepare_sram(node))
+	sram_base_addr = of_iomap(node, 0);
+	if (!sram_base_addr) {
+		pr_err("%s: could not map sram registers\n", __func__);
 		return;
+	}
 
 	if (rockchip_smp_prepare_pmu())
 		return;
 
-	/* enable the SCU power domain */
-	pmu_set_power_domain(PMU_PWRDN_SCU, true);
+	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9) {
+		if (rockchip_smp_prepare_sram(node))
+			return;
 
-	/*
-	 * While the number of cpus is gathered from dt, also get the number
-	 * of cores from the scu to verify this value when booting the cores.
-	 */
-	ncores = scu_get_core_count(scu_base_addr);
+		/* enable the SCU power domain */
+		pmu_set_power_domain(PMU_PWRDN_SCU, true);
+
+		node = of_find_compatible_node(NULL, NULL, "arm,cortex-a9-scu");
+		if (!node) {
+			pr_err("%s: missing scu\n", __func__);
+			return;
+		}
 
-	scu_enable(scu_base_addr);
+		scu_base_addr = of_iomap(node, 0);
+		if (!scu_base_addr) {
+			pr_err("%s: could not map scu registers\n", __func__);
+			return;
+		}
+
+		/*
+		 * While the number of cpus is gathered from dt, also get the
+		 * number of cores from the scu to verify this value when
+		 * booting the cores.
+		 */
+		ncores = scu_get_core_count(scu_base_addr);
+		pr_err("%s: ncores %d\n", __func__, ncores);
+
+		scu_enable(scu_base_addr);
+	} else {
+		asm ("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr));
+		ncores = ((l2ctlr >> 24) & 0x3) + 1;
+	}
 
 	/* Make sure that all cores except the first are really off */
 	for (i = 1; i < ncores; i++)
-- 
1.9.1